CN108140255B - The method and system of reflecting surface in scene for identification - Google Patents
The method and system of reflecting surface in scene for identification Download PDFInfo
- Publication number
- CN108140255B CN108140255B CN201680056908.1A CN201680056908A CN108140255B CN 108140255 B CN108140255 B CN 108140255B CN 201680056908 A CN201680056908 A CN 201680056908A CN 108140255 B CN108140255 B CN 108140255B
- Authority
- CN
- China
- Prior art keywords
- reflecting surface
- scene
- identification
- candidate
- method described
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T19/00—Manipulating 3D models or images for computer graphics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
- G06T7/593—Depth or shape recovery from multiple images from stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/75—Determining position or orientation of objects or cameras using feature-based methods involving models
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2200/00—Indexing scheme for image data processing or generation, in general
- G06T2200/04—Indexing scheme for image data processing or generation, in general involving 3D image data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
- G06T2207/10012—Stereo images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Computer Graphics (AREA)
- Computer Hardware Design (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Length Measuring Devices With Unspecified Measuring Means (AREA)
Abstract
There is provided herein the method and systems of the reflecting surface in scene for identification.The system may include being configured as the sensing device of photographed scene.The system further includes storage device, which is configured as the three-dimensional position of at least some of storage scene object.The system further includes computer processor, and the reflecting surface which is configured to attempt to obtain one or more candidate surfaces of the selection of the surface from scene indicates.In the case where attempting acquisition and being successful situation, computer processor is additionally configured to determine that candidate reflecting surface is strictly the reflecting surface for indicating to limit by surface obtained.According to certain embodiments of the present invention, in the case where attempting calculating and being unsuccessful situation, determine that the identification part of object is the object unrelated with the object stored.
Description
Technical field
Present invention relates generally to field of image processings, and the reflection more particularly, to detection in the scene of shooting
Surface.
Background technique
Before illustrating background of the invention, it may be helpful for illustrating the definition for the certain terms that will be used hereinafter
's.
As used herein term " sensing device " (being referred to as " camera " in computer vision sometimes) is by broadly
It is defined as any combination of any kind of one or more sensors, being not necessarily optical (but may include radar, super
Sound wave etc.).In addition, sensing device is configured as photographed scene image, some three-dimensional datas of scene are obtained or obtained.Example
Property sensing device may include a pair of of camera, which is configured as shooting passive stereo sound, which can be with
Depth data is exported by comparing from the image of different position acquisitions.Another example of sensing device may include structured light
Sensor, the structured light sensor are configured as the anti-of the predefined light pattern that reception and analysis have projected in scene
It penetrates.However another important example is 2D sensing device, multiple 2D images of the 2D sensing device photographed scene are simultaneously further
The space data of relationship between each 2D shooting image are provided.It will be noted that for the purpose of this application, in scene
All dimensions can be and opposite (as long as example, the ratio is to provide from camera or can be derived, then there is relative movement
It is enough).
The interface that as used herein term " reflecting surface " is defined as between two kinds of different media changes wave
Before direction (for example, light or sound) make wavefront back to the surface in the medium of its origin.Mirror-reflection is from surface
Light (or other kinds of wave) mirror reflection, wherein the light (ray) from single incident direction is reflected to single outgoing
Direction.This performance is described by reflection law, which set forth direction (incident ray) and the reflection of incident light
Emergent light direction (indirect ray) it is at the same angle relative to surface normal shape, therefore incidence angle be equal to angle of reflection, and
And incident direction, normal direction and reflection direction are coplanar.Partially reflecting surface can be referred to as any in two types
It is a kind of: type one --- not all surface is all reflexive.The rank of type two --- mirror-reflection can change, and
It can be considered as " can reflect " more than the rank of an appropriate threshold.
The challenge of computer vision first is that the presence of the reflecting surface in detecting field scape and obtaining related reflecting surface
Knowledge.In mirror-reflection more particularly to mirror in the case where, existing risk is, carries out computer based to scene
It is real object that analysis, which can be mistakenly considered the image shot in reflection,.
It is recommended that some logics or process will be advantageous, these logics or process will enable the vision system of computerization
Real object and their own image are enough distinguished, can automatically detect the reflecting surface in the scene of shooting, and more specific
Ground is said, the space representation of reflecting surface can be generated.
Summary of the invention
Some embodiments of the present invention provide the method and system of the reflecting surface in scene for identification.The system can
To include the sensing device for being configured as photographed scene.The system can also include storage device, which is configured as
Store the three-dimensional position of at least some of scene object.The system can also include computer processor, the computer disposal
The reflecting surface that device is configured to attempt to obtain the one or more candidate surfaces selected from the surface in scene indicates.It is tasting
It is in successful situation that examination, which obtains, and computer processor is additionally configured to determine that candidate reflecting surface is strictly by table obtained
Face indicates the reflecting surface limited.According to certain embodiments of the present invention, it in the case where attempting calculating and being unsuccessful situation, determines
The identification part of object is the object unrelated with storage object.
Of the invention these, additional and/or other aspects and/or advantage are illustrated in the following detailed description；It may
It is inferred to from detailed description；And/or practice through the invention learns.
Detailed description of the invention
It is considered as that subject of the present invention is highlighted and is distinctly claimed in the conclusion part of specification.So
And preferably it can pass through ginseng when reading attached drawing about organizing and operating method of the invention and its objects, features and advantages
Examine it is described in detail below understand, in the accompanying drawings:
Fig. 1 is to show the block diagram of the unrestricted exemplary system architecture of some embodiments according to the present invention；
Fig. 2 is to show the high level flow chart of the unrestricted illustrative methods of some embodiments according to the present invention；
Fig. 3 is the ray diagram in terms of showing some optical paths of some embodiments according to the present invention；And
Fig. 4 is to show the example photographed figure of the real scene of several aspects according to certain embodiments of the present invention
Picture.
It will be appreciated that element shown in the accompanying drawings is not drawn necessarily to scale for simple and clear explanation.Example
Such as, for the sake of clarity, the size of some elements may be exaggerated relative to other elements.In addition, thinking suitable place,
Reference label can be repeated among the figures to instruction correspondence or similar element.
Specific embodiment
In the following description, various aspects of the invention will be described.For purposes of explanation, elaborate specifically configure and
Details is in order to provide thorough understanding of the present invention.It is, however, obvious to a person skilled in the art that of the invention
It can be not implementing in the case where detail presented herein.In addition, in order not to the fuzzy present invention, it is convenient to omit or letter
Change well known feature.
Unless expressly stated otherwise, otherwise from following discussion it is readily apparent that it should be understood that in the whole instruction
In, computer or computing system or class are referred to using the discussion of the terms such as " processing ", " operation ", " calculating ", " determination "
As computing electronics movement and/or process, which will be indicated as in the register and/or memory of computing system
The data manipulation of physical quantity (such as amount of electrons) and/or be converted to the memory for being similarly represented as computing system, register or
Other data of physical quantity in other this information storage, transmission or display devices.
Fig. 1 is the block diagram for showing the exemplary architecture that can implement embodiments of the present invention on it.System 100 can be with
The sensing device 110 that may include the scene of object (such as 14) and surface (such as 10) including being configured as shooting.System 100
It can also include the storage device 120 for being configured as the database of maintenance scene, the database purchase of the scene is in the scene
The proximal location of at least some objects and/or surface (for example including object 14).It is important to note that database 120 may be used also
It is known anti-in scene to indicate which object and surface is also reflexive, and when therefore after carrying to ray tracing
Reflective surface is taken into account.
It should be noted that database 120 needs not be 3D in itself, and can actually can save therefrom export
The form of any data structure of the data of the relative position of object in scene.Therefore, the 3D of storage point is not needed actually
Position.For actual purpose, the data that storage can therefrom be inferred to the position 3D are sufficient.One unrestricted example
It is depth map and position and angle from the shooting of this depth map.Such depth map does not provide the position 3D a little
It sets, but can be inferred that the position 3D.
Once such perception reflex surface, it will be added in database, so that it can be used for needing in scene
In the various application programs of the cognition of reflecting surface, or minimally by reflecting surface and " well (well) " or other are flat
" recess " on surface distinguishes.
According to some embodiments, the data of storage are also possible to the 3D model of object, are not necessarily the special object
Real scan, but be located at room in object model.
System 100 can also include computer processor 130, and computer processor is configured to attempt to obtain from scene
Surface (for example, surface 10) selection one or more candidate surfaces reflecting surface indicate.It is successful attempting to obtain
In the case of, computer processor 130 is additionally configured to determine that candidate reflecting surface 10 is strictly to indicate 134 by surface obtained
The reflecting surface of restriction.Alternatively, in the case where attempting to calculate and being unsuccessful situation, determine that the identification part of object is and stores pair
As unrelated new object 132, and it can be used as new entry and be added to storage device 120.
According to certain embodiments of the present invention, identify that the candidate in scene is anti-based on the image of sensing before trial
Reflective surface, and wherein to executing the trial on the candidate identified.
According to certain embodiments of the present invention, the cognition and expression of reflecting surface can be also used for reanalysing previous table
Face, because new surface can change the understanding (in a probabilistic manner) on analysed surface in the scene.Therefore, improvement is executed
With some iterative process for verifying data related with the reflecting surface in scene.
According to certain embodiments of the present invention, the object of candidate reflecting surface on the database by identification storage is identified
One of at least part execute, wherein the identification part of object is not located at position associated with the object stored.
For example, some features of image 12 are identified as, (it is registered in database 120 and its proximal location is in scene with object 14
In be known) similar (in addition to some spaces tilt or translate).
According to certain embodiments of the present invention, identify that candidate reflecting surface is deep by the 3D of identification instruction reflecting surface
Degree pattern is performed.Main " suspection " more specifically, for the surface as reflecting surface is that it is based on image analysis
Depth analysis be similar to boundary in other flat surfaces and be clearly recessed or the surface of " well ".Reflecting surface or mirror provide
The depth concept of similar this recess, and pair shown in the surface for being suspect to be surface by analysis and rear orientation trace
As reflecting surface and true recess are distinguished.In the case where this is the true recess in concrete surface, object will be located
In its " true " position.Only in case of reflection, real object is in different positions, and sensing device actually refers to
To the image of real object.
According to certain embodiments of the present invention, in the case where determining candidate reflecting surface is reflecting surface, computer
Processor is additionally configured to indicate to generate the virtual image for the virtual objects being located in scene based on reflecting surface.
According to certain embodiments of the present invention, it would be possible to be considered as the opposite figure of anchor point with wherein at least one image
Requirement as replacing the position 3D of above-mentioned object.In this way, it would be possible to derive the confined volume that reflecting surface is located at.This will
It is realized by the backward ray tracing of the above-mentioned light ray of application.In this case, exact surface expression will be not total
It all derives, but some tolerances or volume range will be provided for its position, and still may answer many
It is beneficial with program.For example, it is enough to know that the particular range in scene is limited sometimes in path planning application program, and
And the accurate location of confined surfaces (reflecting surface) is not needed.
Fig. 2 is to show for identification the side of the reflecting surface of such as mirror and other planes and nonplanar reflecting surface
The high level flow chart of the method 200 of method.Method 200 may include at least one image of scene of the sensing comprising surface and object
Step 210；Meanwhile this method can safeguard the three of at least some of the storage scene scene of the three-dimensional position 220 of object
Dimensional database；Followed by iteration subprocess, method 200 attempt to obtain one or more candidate lists of the surface selection from scene
The reflecting surface in face indicates 230.It executes and attempts whether successfully to check 240.Then, in the case where attempting acquisition and being successful situation,
Determine that candidate's reflecting surface is the reflecting surface 250 for indicating to limit by surface obtained.Some embodiment party according to the present invention
Formula, surface indicate to be realized by the numerical approximation value of surface equation.It should be noted that scene may be included known
Mirror, therefore to the calculating of new potential reflecting surface may in view of they and may store it in database.
According to certain embodiments of the present invention, in the case where attempting calculating and being unsuccessful situation, the Identification Division of object is determined
Dividing is the object 260 unrelated in the object stored.
According to certain embodiments of the present invention, by identifying the time in scene based on the image of sensing before trial
Reflecting surface is selected, and wherein to executing the trial on the candidate identified.
According to certain embodiments of the present invention, at least part of one of object by identification storage on the database
Candidate reflecting surface is identified to execute, and wherein the identification part of object is not located at position associated with the object stored.
According to certain embodiments of the present invention, the 3D depth pattern for indicating reflecting surface includes that accurately depth walks for linking
Suddenly.
According to certain embodiments of the present invention, wherein in the case where candidate reflecting surface is determined as reflecting surface,
It is described to export by the way that image processing algorithm to be applied to the identification part of the corresponding object of object and storage in the database
The albedo parameters of reflecting surface.
According to certain embodiments of the present invention, albedo parameters further include the unreflecting part on perception reflex surface.
According to certain embodiments of the present invention, wherein albedo parameters include the rank and type of reflectivity.
According to certain embodiments of the present invention, it in the case where candidate reflecting surface is determined as reflecting surface, is based on
Reflecting surface indicates to generate the virtual image of the virtual objects in scene.In addition, by analyzing derived reflection characteristic
For generating the photorealism of the virtual objects integrated in scene.
Fig. 3 is the ray diagram 300 for showing some aspects of the optical path of embodiment according to the present invention.Specifically, sensing
The sensor array 50 of device is shown as the transversal of the part 60 of the projection with the doubtful image for indicating the object in scene
Face.When attempting is the doubtful framing reflecting surface expression of known real object 70 for position in the scene, Ke Yicong
310 rear orientation trace of ray to potential reflecting surface 330B is arrived real object 70 by the focus 40 of sensing device again, and assuming that
Reflection law is abided by when the surface normal 340B of potential reflecting surface 330B.For another possibility with surface normal 340A
Reflecting surface 330A, the process can be iteratively repeated.
The above process be used to map candidate reflecting surface, wherein the known location of real object 70, surface normal and anti-
Law is penetrated as constraint condition, by the constraint condition, potential reflecting surface is based on reflecting surface 330A etc., and gradually generation is latent
Reflecting surface.
Fig. 4 is the example photographed image for showing the real scene of several aspects of embodiment according to the present invention.By
It is detected as image 430B in some objects of such as lamp 430A, so scene seems to include flat mirror 410.In addition, scheming
Other objects not shot as in, (such as picture 420 (describing eyes)) can be stored in database with its accurate position 3D
In.When attempting the expression of export reflecting surface, the sensor array of the sensing device from picture 420 to camera is executed as described above
The ray rear orientation trace of column.
Once may indicate that it can be used due to the numerical approximation value on surface or the plane equation export reflecting surface of mirror
In the image for the virtual objects that reflection is introduced into scene.For example, can be introduced cylindrical body 450A as augmented reality object
Into scene.In order to make user more realistically perceive virtual objects, in the reflection law for abiding by reflecting surface detected and its
Its respective reflection 450B is generated while his optical property.
In the above description, embodiment is example or realization of the invention." embodiment ", " embodiment " or
The various appearances of " some embodiments " are not necessarily all referring to identical embodiment.
Although various features that can be of the invention in the described in the text up and down of single embodiment, feature can also be single
Solely or in any suitable combination provide.On the contrary, although for the sake of clarity the present invention can be in individual embodiment
Upper and lower described in the text, but the present invention can also realize in single embodiment.
To " some embodiments ", " embodiment ", " embodiment " or " other embodiments " in specification
Reference means that a particular feature, structure, or characteristic for combining embodiment description is included at least some embodiments but not
It must be all of the embodiments of the present invention.
It should be understood that wording as used herein and term are not necessarily to be construed as limiting, and it is only used for descriptive mesh
's.
With reference to it is appended description, drawings and embodiments may be better understood present invention teach that principle and purposes.
It should be understood that details set forth herein does not explain the limitation to application of the invention.
Further, it is understood that the present invention can be practiced or carried out in various ways, and the present invention can divided by
It is realized in embodiment except the embodiment summarized in upper description.
Should be understood that term " includes ", "comprising", " by ... form " and its grammatical variants be not excluded for addition one
A or multiple components, feature, step or its entirety or group, and term should be interpreted assignment component, feature, step or whole
Body.
If specification or claim are related to " adding " element, more than one add ons are not excluded the presence of.
It should be understood that in the case where claim or specification mention "one" or "one" element, it is such
With reference to not being interpreted that there is only one in the element.
It, " can with " or " can it should be understood that in specification Statement component, feature, structure or characteristic " possibility " " perhaps "
In the case that energy " is included, do not need to include specific component, feature, structure or characteristic.
Under applicable circumstances, although state diagram, flow chart or both can be used to describe embodiment, this hair
It is bright to be not limited to these figures or corresponding description.For example, process does not need the frame or state by each diagram, or with diagram
It is mobile with the identical sequence of sequence of description.
Method of the invention can execute or complete selected step or task by manual, automatic or combinations thereof come real
It is existing.
Description, example, method and the material presented in claims and specification be not necessarily to be construed as it is restrictive,
And it is merely illustrative.
Unless otherwise defined, the meaning of technical and scientific terms used herein is usually by of the art common
Technical staff is generally understood.
The present invention can in test or practice with method described herein and material be equivalent or similar method and material
Material is to implement.
Although the embodiment for being directed to limited quantity describes the present invention, these are not necessarily to be construed as to this hair
The limitation of bright range, but the example as some preferred embodiments.Other possible variations modify and apply also at this
In the range of invention.Therefore, the scope of the present invention should not be limited by content described so far, but by appended power
Benefit requires and its legal equivalents limit.
Claims (18)
1. a kind of method of the reflecting surface in scene for identification, comprising:
At least one image of scene of the sensing comprising surface and object；
Safeguard the object database of the scene, at least the one of some objects of the database purchase in the scene
Partial position；
Pass through the rear portion assigned to ray tracing from the Identification Division of object described at least one of described scene with the object
At least one optical path of associated the stored position of split-phase come attempt to obtain the surface from the scene selection one
The reflecting surface expression of a or multiple candidate reflecting surfaces,
Wherein, in the case where the acquisition attempted is successful situation, determine that at least one candidate reflecting surface is by obtained anti-
Reflective surface indicates the reflecting surface limited, and
Generate the image of the object in the scene for being introduced into and indicating reflection by the reflecting surface.
2. according to the method described in claim 1, wherein, the numerical value by the surface equation based on the backward ray tracing is close
Realize that the reflecting surface is indicated like value.
3. according to the method described in claim 1, wherein, before the trial, being identified based on the image sensed described
The candidate reflecting surface in scene, and wherein, the trial is executed to the candidate identified.
4. according to the method described in claim 1, wherein, storing one of described object on the database at least by identification
A part executes the identification to the candidate reflecting surface, wherein the part of the object recognized is not located at and is deposited
At the associated position of the object of storage.
5. according to the method described in claim 4, wherein, indicating the 3D depth pattern of the reflecting surface by identification to execute
Identification to the candidate reflecting surface.
6. according to the method described in claim 5, wherein, indicating that the 3D depth pattern of the reflecting surface includes that boundary is specific
Well.
7. according to the method described in claim 1, wherein, in the case where the calculating attempted is unsuccessful situation, it is described right to determine
The identification part of elephant is the object unrelated with the object stored.
8. according to the method described in claim 7, the object newly recognized is also added to database.
9. according to the method described in claim 1, wherein, in the feelings that the candidate reflecting surface is determined as to the reflecting surface
Under condition, by the way that image processing techniques to be applied to the identification part of the object and is stored in corresponding on the database
Object exports the albedo parameters of the reflecting surface.
10. according to the method described in claim 9, wherein, the albedo parameters further include identifying the reflecting surface not
The part of reflection.
11. according to the method described in claim 9, wherein, the albedo parameters include the rank and type of reflectivity.
12. according to the method described in claim 1, wherein, the case where the candidate reflecting surface is determined as reflecting surface
Under, the virtual image for the virtual objects that rendering is located in the scene is indicated based on the reflecting surface.
13. a kind of system of the reflecting surface in scene for identification, comprising:
Camera is configured as at least one image of scene of the sensing comprising surface and object；
Memory is configured as safeguarding that the database of the scene, the database purchase are some described in the scene
At least part of position of object；And
Computer processor is configured as the identification by rear to ray tracing from object described at least one of described scene
It attempts to obtain from the scene at least one optical path of stored position associated with the part of the object in part
In the reflecting surface of the candidate reflecting surfaces of one or more of surface selection indicate；
Wherein, in the case where the acquisition attempted is successful situation, the computer processor is additionally configured to determine candidate reflection
Surface is the reflecting surface for indicating to limit by surface obtained
Wherein, the computer processor is additionally configured to generate in the scene for being introduced into and indicating reflection by the reflecting surface
The image of object.
14. system according to claim 13, wherein before the trial, based on the image sensed to identify
The candidate reflecting surface in scene is stated, and wherein, the trial is executed to the candidate identified.
15. system according to claim 14, wherein by recognizing one of the object being stored on the database
At least part execute the identification to the candidate reflecting surface, wherein the part of the object recognized is not located at
At position associated with the object stored.
16. system according to claim 14, wherein indicate the 3D depth pattern of the reflecting surface by identification to hold
Identification of the row to the candidate reflecting surface.
17. system according to claim 13, wherein in the case where the calculating attempted is unsuccessful situation, described in determination
The identification part of object is the object unrelated with the object stored.
18. system according to claim 13, wherein the candidate reflecting surface is being determined as the reflecting surface
In the case of, the computer processor is additionally configured to indicate to generate based on the reflecting surface virtual in the scene
The virtual image of object.
Applications Claiming Priority (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US14/872,160 | 2015-10-01 | ||
| US14/872,160 US10049303B2 (en) | 2015-10-01 | 2015-10-01 | Method and a system for identifying reflective surfaces in a scene |
| PCT/IL2016/051062 WO2017056089A2 (en) | 2015-10-01 | 2016-09-27 | Method and a system for identifying reflective surfaces in a scene |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108140255A CN108140255A (en) | 2018-06-08 |
| CN108140255B true CN108140255B (en) | 2019-09-10 |
Family
ID=58422968
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201680056908.1A Active CN108140255B (en) | 2015-10-01 | 2016-09-27 | The method and system of reflecting surface in scene for identification |
Country Status (3)
| Country | Link |
|---|---|
| US (3) | US10049303B2 (en) |
| CN (1) | CN108140255B (en) |
| WO (1) | WO2017056089A2 (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108780228B (en) * | 2016-01-19 | 2021-04-20 | 奇跃公司 | Augmented reality system and method using images |
| US9868212B1 (en) * | 2016-02-18 | 2018-01-16 | X Development Llc | Methods and apparatus for determining the pose of an object based on point cloud data |
| KR102522502B1 (en) | 2016-04-26 | 2023-04-17 | 매직 립, 인코포레이티드 | Electromagnetic tracking with augmented reality systems |
| US10594920B2 (en) * | 2016-06-15 | 2020-03-17 | Stmicroelectronics, Inc. | Glass detection with time of flight sensor |
| CN108416837A (en) * | 2018-02-12 | 2018-08-17 | 天津大学 | Trivector Database Modeling method in ray trace |
| KR20200018207A (en) * | 2018-08-10 | 2020-02-19 | 일렉트로닉 아트 아이엔씨. | Systems and methods for rendering reflections |
| US11043025B2 (en) | 2018-09-28 | 2021-06-22 | Arizona Board Of Regents On Behalf Of Arizona State University | Illumination estimation for captured video data in mixed-reality applications |
| US10839560B1 (en) * | 2019-02-26 | 2020-11-17 | Facebook Technologies, Llc | Mirror reconstruction |
| US11462000B2 (en) * | 2019-08-26 | 2022-10-04 | Apple Inc. | Image-based detection of surfaces that provide specular reflections and reflection modification |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1630892A (en) * | 2002-02-12 | 2005-06-22 | 日本发条株式会社 | Identifying medium and identifying method for object |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7973790B2 (en) | 2005-08-11 | 2011-07-05 | Realtime Technology Ag | Method for hybrid rasterization and raytracing with consistent programmable shading |
| US8432395B2 (en) * | 2009-06-16 | 2013-04-30 | Apple Inc. | Method and apparatus for surface contour mapping |
| US20150185857A1 (en) | 2012-06-08 | 2015-07-02 | Kmt Global Inc | User interface method and apparatus based on spatial location recognition |
| US9600927B1 (en) * | 2012-10-21 | 2017-03-21 | Google Inc. | Systems and methods for capturing aspects of objects using images and shadowing |
| US9874749B2 (en) * | 2013-11-27 | 2018-01-23 | Magic Leap, Inc. | Virtual and augmented reality systems and methods |
| US9035946B1 (en) | 2014-02-13 | 2015-05-19 | Raycast Systems, Inc. | Computer hardware architecture and data structures for triangle binning to support incoherent ray traversal |
| US10210628B2 (en) | 2014-03-03 | 2019-02-19 | Mitsubishi Electric Corporation | Position measurement apparatus for measuring position of object having reflective surface in the three-dimensional space |
-
2015
- 2015-10-01 US US14/872,160 patent/US10049303B2/en active Active
-
2016
- 2016-09-27 CN CN201680056908.1A patent/CN108140255B/en active Active
- 2016-09-27 WO PCT/IL2016/051062 patent/WO2017056089A2/en active Application Filing
-
2018
- 2018-08-09 US US16/059,865 patent/US10395142B2/en active Active
-
2019
- 2019-08-13 US US16/539,502 patent/US10719740B2/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1630892A (en) * | 2002-02-12 | 2005-06-22 | 日本发条株式会社 | Identifying medium and identifying method for object |
Also Published As
| Publication number | Publication date |
|---|---|
| US10049303B2 (en) | 2018-08-14 |
| WO2017056089A3 (en) | 2017-07-27 |
| US20180357516A1 (en) | 2018-12-13 |
| CN108140255A (en) | 2018-06-08 |
| US20190370612A1 (en) | 2019-12-05 |
| US10719740B2 (en) | 2020-07-21 |
| US10395142B2 (en) | 2019-08-27 |
| WO2017056089A2 (en) | 2017-04-06 |
| US20170098139A1 (en) | 2017-04-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108140255B (en) | The method and system of reflecting surface in scene for identification | |
| US9303525B2 (en) | Method and arrangement for multi-camera calibration | |
| JP5024067B2 (en) | Face authentication system, method and program | |
| CN113196296A (en) | Detecting objects in a crowd using geometric context | |
| MacLean et al. | Recovery of egomotion and segmentation of independent object motion using the EM-algorithm | |
| CN110998658A (en) | Depth map using structured light and flood light | |
| Takimoto et al. | 3D reconstruction and multiple point cloud registration using a low precision RGB-D sensor | |
| US9990710B2 (en) | Apparatus and method for supporting computer aided diagnosis | |
| CN104662561A (en) | Skin-based user recognition | |
| CN108876835A (en) | Depth information detection method, device and system and storage medium | |
| CN103562934A (en) | Face location detection | |
| US10474232B2 (en) | Information processing method, information processing apparatus and user equipment | |
| Canessa et al. | A dataset of stereoscopic images and ground-truth disparity mimicking human fixations in peripersonal space | |
| Wang et al. | Accuracy of monocular gaze tracking on 3d geometry | |
| CN108475434A (en) | The method and system of radiation source characteristic in scene is determined based on shadowing analysis | |
| Governi et al. | Improving surface reconstruction in shape from shading using easy-to-set boundary conditions | |
| EP2120206A1 (en) | Object shape generating method, object shape generating device and program | |
| CN103268474A (en) | Three-dimensional scanning imaging device of mobile phone or tablet personal computer | |
| US10048752B2 (en) | Information processing method, information processing apparatus and user equipment | |
| Hirofuji et al. | 3D reconstruction of specular objects with occlusion: A shape-from-scattering approach | |
| Rodríguez | A methodology to develop computer vision systems in civil engineering: Applications in material testing and fish tracking | |
| Burns | Matching two-dimensional images to multiple three-dimensional objects using view description networks | |
| Körtgen | Robust automatic registration of range images with reflectance | |
| US20100054608A1 (en) | Surface Extraction Method, Surface Extraction Device, and Program | |
| CN117456396A (en) | Infrared light spot identification method, device, system and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20200131 Address after: 3 / F, No.20, galiarehapura, helzria, Israel Patentee after: Alibaba (Israel) Technology Co.,Ltd. Address before: Paktikwa, Israel Patentee before: Infinity Augmented Reality Israel Ltd. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230410 Address after: Room 516, floor 5, building 3, No. 969, Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province Patentee after: Alibaba Dharma Institute (Hangzhou) Technology Co.,Ltd. Address before: 3 / F, No.20, galiarehapura, helzria, Israel Patentee before: Alibaba (Israel) Technology Co.,Ltd. |